Using geographical information systems and neural networks to predict fuel moisture in homogeneous fuels
AuthorBall, Barbara Jean, 1955-
Agriculture, Forestry and Wildlife.
MetadataShow full item record
PublisherThe University of Arizona.
RightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
AbstractComputer models used to predict the pattern and rate of spread of fire in grasslands as well as other vegetation types rely on various inputs for their calculations. Because of the direct effect they have on the quantity of fuel available to carry a fire and the effects of moisture on the potential for fuel available to carry a fire and the effects of moisture on the potential for fuel to begin burning and to sustain a fire, fuel loading measurements, which are similar to production measurements in grasslands, and estimates of fuel moisture are two important variables to be considered when modeling fire behavior. The objective of this project is to determine if there is a relationship between measured environmental variables and the fuel moisture values at the same sample points which can be modeled with GIS data and neural networks. This study was carried out using a combination of field sampled data and common GIS data layers. The results demonstrate the potential for neural network analysis in this type of environmental problem.
Degree ProgramGraduate College
Renewable natural resources